English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Replication studies are essential for validation of new methods, and arecrucial to maintain the high standards of scientific publications, and to usethe results in practice. We have attempted to replicate the main method in'Development and validation of a deep learning algorithm for detection ofdiabetic retinopathy in retinal fundus photographs' published in JAMA 2016;316(22). We re-implemented the method since the source code is not available,and we used publicly available data sets. The original study used non-publicfundus images from EyePACS and three hospitals in India for training. We used adifferent EyePACS data set from Kaggle. The original study used the benchmarkdata set Messidor-2 to evaluate the algorithm's performance. We used the samedata set. In the original study, ophthalmologists re-graded all images fordiabetic retinopathy, macular edema, and image gradability. There was onediabetic retinopathy grade per image for our data sets, and we assessed imagegradability ourselves. Hyper-parameter settings were not described in theoriginal study. But some of these were later published. We were not able toreplicate the original study. Our algorithm's area under the receiver operatingcurve (AUC) of 0.94 on the Kaggle EyePACS test set and 0.80 on Messidor-2 didnot come close to the reported AUC of 0.99 in the original study. This may becaused by the use of a single grade per image, different data, or different notdescribed hyper-parameter settings. This study shows the challenges ofreplicating deep learning, and the need for more replication studies tovalidate deep learning methods, especially for medical image analysis.  Our source code and instructions are available at:https://github.com/mikevoets/jama16-retina-replication

Replication study: Development and validation of deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs